Mistral-Large-3-675B-Instruct-2512 IQ1_S

This file is exactly 142,267,169,760 bytes — 132.50 GiB / 142.27 GB at an effective 1.690 bits per weight. The nominal rate for IQ1_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 4 file(s), summed

Get it

132.50 GiB · 4 files
llama.cpp
llama-cli -hf bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF:IQ1_S

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download bartowski/mistralai_Mistral-Large-3-675B-Instruct-2512-GGUF --include "mistralai_Mistral-Large-3-675B-Instruct-2512-IQ1_S/mistralai_Mistral-Large-3-675B-Instruct-2512-IQ1_S-*-of-*.gguf"

This quantization is split across 4 files totalling 132.50 GiB. You need every part — the first is not a smaller version of the model.

Size
132.50 GiB
142.27 GB
Effective bpw
1.690
from real bytes ÷ params
Tensors
Header
GGUF metadata